• Earthquakes and Structures
• /
• v.12 no.6
• /
• pp.591-601
• /
• 2017

To prevent or limit the damage caused by earthquakes on existing buildings, several retrofitting techniques are possible. In this work, an ultra high performance concrete based on sand dune has been formulated for use in the reinforcement of a multifunctional tower in the city of Skikda in Algeria. Tests on the formulated ultra high performance concrete are performed to determine its characteristics. A nonlinear dynamic analysis, based on the "Pushover" method was conducted. The analysis allowed an optimization of the width of reinforced concrete walls used in seismic strengthening. Two types of concrete are studied, the ordinary concrete and the ultra high performance concrete. Both alternatives are compared with the reinforcement with carbon fibers and by base isolation retrofit design.

• Proceedings of the KIEE Conference
• /
• 2002.07d
• /
• pp.2167-2170
• /
• 2002

In this paper, model-based tuning rules of the PID controller are proposed incorporating with genetic algorithms. Three sets of optimal PID parameters for set-point tracking are obtained based on the first-order time delay model and a genetic algorithm as a optimization tool which minimizes performance indices(IAE, ISE and ITAE). Then tuning rules are derived using the tuned parameter sets, potential rule models and a genetic algorithm. Simulation is carried out to verify the effectiveness of the proposed rules.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.8 no.6
• /
• pp.58-69
• /
• 1998

This paper introduces a novel neuro-fuzzy system based on the polynomial fuzzy neural network(PFNN) architecture. The PFNN consists of a set of if-then rules with appropriate membership functions whose parameters are optimized via a hybrid genetic algorithm. A polynomial neural network is employed in the defuzzification scheme to improve output performance and to select appropriate rules. A performance criterion for model selection, based on the Group Method of DAta Handling is defined to overcome the overfitting problem in the modeling procedure. The hybrid genetic optimization method, which combines a genetic algorithm and the Simplex method, is developed to increase performance even if the length of a chromosome is reduced. A novel coding scheme is presented to describe fuzzy systems for a dynamic search rang in th GA. For a performance assessment of the PFNN inference system, three well-known problems are used for comparison with other methods. The results of these comparisons show that the PFNN inference system outperforms the other methods while it exhibits exceptional robustness characteristics.

• MALSORI
• /
• no.66
• /
• pp.73-86
• /
• 2008

Beamforming is one of the spatial filtering techniques which extract only desired signals from noisy environments using microphone arrays. Fixed beamforming is a simple concept and easy to implement. However, it does not show good performance in real noisy conditions. As an adaptive beamforming, Frost algorithm can be a good candidate. It uses the concept of the linearly constrained minimum variance (LCMV) algorithm. The difference between the Frost and the LCMV algorithm is the error correction scheme which is very effective feature in the aspect of performance. In this paper, as quadrature mirror filtering (QMF)-based filterbank is utilized as the pre-processing of the Frost beamformning, the filter length and the learning rate of each band is optimized to improve the performance. The performance is measured by the signal-to-noise ratio (SNR) and the Bark's scale spectral distortion (BSD).

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.5 no.3
• /
• pp.263-267
• /
• 2005

Building classifiers for financial real-world classification problems is often plagued by severely overlapping and highly skewed class distribution. New performance measures such as receiver operating characteristic (ROC) curve and area under ROC curve (AUC) have been recently introduced in evaluating and building classifiers for those kind of problems. They are, however, in-effective to evaluation of classifier's discrimination performance in a particular class of the classification problems that interests lie in only a local operating range of the classifier, In this paper, a new method is proposed that enables us to directly improve classifier's discrimination performance at a desired local operating range by defining and optimizing a partial area under ROC curve or domain-specific curve, which is difficult to achieve with conventional classification accuracy based learning methods. The effectiveness of the proposed approach is demonstrated in terms of fraud detection capability in a real-world fraud detection problem compared with the MSE-based approach.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.19 no.5
• /
• pp.251-257
• /
• 2024

Securing various types of training data in image Classification is important for improving performance. However, increasing the amount of original data is cost-limited, so data diversity can be secured by transforming images through data augmentation. Recently, a new deep learning approach using Generative AI models like GAN or Diffusion Based models has emerged in the Data Augmentation task, and reinforcement learning-based methods such as AutoAugment and Deep AutoAugment using existing basic Augmentation techniques are also showing good performance. However, this method has the disadvantage of having a complicated optimization procedure and high computational cost. This paper conducted various experiments with existing methods Cutmix, Mixup, RandAugment. By combining these techniques appropriately, we obtained higher performance than existing method without much effort. Additionally, our ablation experiment shows that additional hyper-parameter adjustments are needed for the basic augmentation types when we use RandAugment. Our code is available at https://github.com/lliee1/Randomness_Analysis.

• International conference on construction engineering and project management
• /
• 2024.07a
• /
• pp.988-995
• /
• 2024

With the modern workplace's increasing dependence on computer-based tasks, traditional lighting standards have been identified as insufficient for optimal occupant comfort and productivity. Therefore, this paper presents a comprehensive system framework designed to manage visual fatigue and cognitive performance within office environments. Classification and regression models using gradient boosting machine and random forest to predict visual fatigue and cognitive performance were developed based on data collected from 16 subjects in experiments. To this end, the proposed system consists of two modules: the first module predicts visual fatigue and cognitive performance levels using classification models, offering immediate feedback to occupants. The second module, targeted at facility managers, uses regression models and a genetic algorithm to identify optimal lighting settings, aiming to minimize visual fatigue and enhance cognitive performance. This system can help to manage visual fatigue and cognitive performance simultaneously, contributing to improvement of eye health and productivity.

• Journal of the Korea Society for Simulation
• /
• v.32 no.3
• /
• pp.67-74
• /
• 2023

A semiconductor fabrication facility(FAB) is one of the most capital-intensive and large-scale manufacturing systems which operate under complex and uncertain constraints through hundreds of fabrication steps. To improve fab performance with intuitive scheduling, practitioners have used weighted-sum scheduling. Since the determination of weights in the scheduling significantly affects fab performance, they often rely on simulation-based decision making for obtaining optimal weights. However, a large-scale and high-fidelity simulation generally is time-intensive to evaluate with an exhaustive search. In this study, we investigated three sampling methods (i.e., Optimal latin hypercube sampling(OLHS), Genetic algorithm(GA), and Decision tree based sequential search(DSS)) for the optimization. Our simulation experiments demonstrate that: (1) three methods outperform greedy heuristics in performance metrics; (2) GA and DSS can be promising tools to accelerate the decision-making process.

• Steel and Composite Structures
• /
• v.47 no.2
• /
• pp.147-165
• /
• 2023

The paper contrasts conventional seismic design with a design that incorporates buckling-restrained bracing in three-dimensional reinforced concrete buildings (BRBs). The suboptimal structures may be found using the multi-objective chimp optimization algorithm (MEN-ChOA). Given the constraints and dimensions, ChOA suffers from a slow convergence rate and tends to become stuck in local minima. Therefore, the ChOA is improved by niching and evolutionary operators to overcome the aforementioned problems. In addition, a new technique is presented to compute seismic and dead loads that include all of a structure's parts in an algorithm for three-dimensional frame design rather than only using structural elements. The performance of the constructed multi-objective model is evaluated using 12 standard multi-objective benchmarks proposed in IEEE congress on evolutionary computation. Second, MEN-ChOA is employed in constructing several reinforced concrete structures by the Mexico City building code. The variety of Pareto optimum fronts of these criteria enables a thorough performance examination of the MEN-ChOA. The results also reveal that BRB frames with comparable structural performance to conventional moment-resistant reinforced concrete framed buildings are more cost-effective when reinforced concrete building height rises. Structural performance and building cost may improve by using a nature-inspired strategy based on MEN-ChOA in structural design work.

• Journal of the Korea Society for Simulation
• /
• v.23 no.4
• /
• pp.9-19
• /
• 2014

The automotive industry has made much efforts to deliver finished vehicles to customers with speed and reliability. Decreasing the time a vehicle stays within an assembly plant from production release to shipment contributes to reduce the total order lead-time and consequently, the total transportation cost as well. Conventional shipment planning algorithms are limited in accommodating the dynamics of assembly plant operations as to finished vehicle shipment. This paper presents a market-based multi-agent shipment planning algorithm to optimize the performance of vehicle shipment process, capturing the operationally disruptive events. Experimental results using simulation show that the algorithm improves vehicle shipment performance with respect to lead time, labor efficiency, finished product quality, and transportation efficiency.